Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2654 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2406. Min Range: -3.2406

Max Act: 3.0809. Min Act: -0.0001

Data Index: 1297964 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 3.2406. Min Range: -3.2406

Max Act: 3.2161. Min Act: -0.0001

Data Index: 1215640 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 3.2406. Min Range: -3.2406

Max Act: 3.0699. Min Act: -0.0001

Data Index: 785181 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 3.2406. Min Range: -3.2406

Max Act: 3.2406. Min Act: -0.0001

Data Index: 509343 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 3.2406. Min Range: -3.2406

Max Act: 3.0830. Min Act: -0.0001

Data Index: 891489 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 3.2406. Min Range: -3.2406

Max Act: 3.2062. Min Act: -0.0001

Data Index: 93327 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 3.2406. Min Range: -3.2406

Max Act: 3.0235. Min Act: -0.0001

Data Index: 759178 (C4 (Web Text))

Max Activating Token Index: 387

Text #7

Max Range: 3.2406. Min Range: -3.2406

Max Act: 2.7291. Min Act: -0.0001

Data Index: 878066 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 3.2406. Min Range: -3.2406

Max Act: 2.7751. Min Act: -0.0001

Data Index: 919626 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 3.2406. Min Range: -3.2406

Max Act: 2.8685. Min Act: -0.0001

Data Index: 1166322 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 3.2406. Min Range: -3.2406

Max Act: 2.6785. Min Act: -0.0001

Data Index: 338599 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 3.2406. Min Range: -3.2406

Max Act: 2.7377. Min Act: -0.0001

Data Index: 564679 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 3.2406. Min Range: -3.2406

Max Act: 2.8555. Min Act: -0.0001

Data Index: 1171222 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 3.2406. Min Range: -3.2406

Max Act: 2.6779. Min Act: -0.0001

Data Index: 71069 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 3.2406. Min Range: -3.2406

Max Act: 2.6521. Min Act: -0.0001

Data Index: 617285 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 3.2406. Min Range: -3.2406

Max Act: 2.3125. Min Act: -0.0001

Data Index: 997744 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 3.2406. Min Range: -3.2406

Max Act: 2.7061. Min Act: -0.0001

Data Index: 164728 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 3.2406. Min Range: -3.2406

Max Act: 2.1416. Min Act: -0.0001

Data Index: 1147391 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 3.2406. Min Range: -3.2406

Max Act: 2.1988. Min Act: -0.0001

Data Index: 945686 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 3.2406. Min Range: -3.2406

Max Act: 2.3032. Min Act: -0.0001

Data Index: 1327288 (C4 (Web Text))

Max Activating Token Index: 349